def test_override_default_params(self):
for key, val in defaults.REDIS_PARAMS.items():
self.expected_params[key] = self.settings['REDIS_PARAMS'][key] = object()
server = from_settings(self.settings)
assert server is self.redis_cls.return_value
self.redis_cls.assert_called_with(**self.expected_params)
def from_settings(cls, settings):
server = connection.from_settings(settings)
# create one-time key. needed to support to use this
# class as standalone dupefilter with scrapy's default scheduler
# if scrapy passes spider on open() method this wouldn't be needed
key = "dupefilter:%s" % int(time.time())
return cls(server, key)
def from_settings(cls, settings):
kwargs = {
'persist': settings.getbool('SCHEDULER_PERSIST'),
'flush_on_start': settings.getbool('SCHEDULER_FLUSH_ON_START'),
'idle_before_close':
settings.getint('SCHEDULER_IDLE_BEFORE_CLOSE'),
}
# If these values are missing, it means we want to use the defaults.
optional = {
# TODO: Use custom prefixes for this settings to note that are
# specific to scrapy-redis.
'queue_key': 'SCHEDULER_QUEUE_KEY',
'queue_cls': 'SCHEDULER_QUEUE_CLASS',
'dupefilter_key': 'SCHEDULER_DUPEFILTER_KEY',
# We use the default setting name to keep compatibility.
'dupefilter_cls': 'DUPEFILTER_CLASS',
'serializer': 'SCHEDULER_SERIALIZER',
}
for name, setting_name in optional.items():
val = settings.get(setting_name)
if val:
kwargs[name] = val
# Support serializer as a path to a module.
if isinstance(kwargs.get('serializer'), six.string_types):
kwargs['serializer'] = importlib.import_module(
kwargs['serializer'])
# Redis Server connection
server = connection.from_settings(settings)
# Ensure the connection is working.
server.ping()
return cls(server=server, settings=settings, **kwargs)
class GxzfcgFactorySpider(RedisSpider):
name = "gxzfcg_spider"
name_pre = 'gxzfcg'
redis_server = connection.from_settings(settings)
def parse(self, response):
node_name_pre = settings['NODE_NAME']
website_pre = '广西壮族自治区政府采购网'
level_pre = response.xpath('//*[@id="channelBody"]/div[1]/a[2]/text()').extract()[0]
typr_pre = response.xpath('//*[@id="channelBody"]/div[1]/a[3]/text()').extract()[0]
ul = response.xpath("//*[@id=\"channelBody\"]/div[2]/ul/li")
for li in ul:
item = TenderItem()
item['node_name'] = node_name_pre
item['website'] = website_pre
item['level'] = level_pre
item['type'] = typr_pre
item['title'] = li.xpath("a/@title").extract()[0]
item['date'] = li.xpath("span[@class=\"date\"]/text()").extract()[0]
item['url'] = 'http://www.gxzfcg.gov.cn' + li.xpath("a/@href").extract()[0]
article = newspaper.Article(
'http://www.gxzfcg.gov.cn' + li.xpath("a/@href").extract()[0],
language='zh', fetch_images=False)
article.download()
article.parse()
item['content'] = article.text
# 生成时间
now_time = datetime.datetime.now().strftime("%Y-%m-%d %H:%M:%S")
item['add_time'] = now_time
item['update_time'] = now_time
# print(item)
yield item
def test_override_default_params(self):
for key, val in DEFAULT_PARAMS.items():
self.expected_params[key] = self.settings['REDIS_PARAMS'][key] = object()
server = from_settings(self.settings)
assert server is self.redis_cls.return_value
self.redis_cls.assert_called_with(**self.expected_params)
def setup_redis(self):
"""Setup redis connection and idle signal.
This should be called after the spider has set its crawler object.
"""
if not self.redis_key:
self.redis_key = '%s:start_urls' % self.name
self.server = connection.from_settings(self.crawler.settings)
# idle signal is called when the spider has no requests left,
# that's when we will schedule new requests from redis queue
self.crawler.signals.connect(self.spider_idle,
signal=signals.spider_idle)
self.crawler.signals.connect(self.schedule_rest_requests,
signal=signals.item_scraped)
self.crawler.signals.connect(self.schedule_rest_requests,
signal=signals.item_dropped)
self.crawler.signals.connect(self.schedule_rest_requests,
signal=signals.request_scheduled)
self.crawler.signals.connect(self.schedule_rest_requests,
signal=signals.response_received)
self.crawler.signals.connect(self.schedule_rest_requests,
signal=signals.response_downloaded)
self.crawler.signals.connect(self.__start_loop,
signal=signals.spider_opened)
self.crawler.signals.connect(self.__stop_loop,
signal=signals.spider_closed)
log.msg("Reading URLs from redis list '%s'" % self.redis_key,
level=log.INFO)
self.touch()
def __init__(self, settings, crawler):
RetryMiddleware.__init__(self, settings)
self.redis = connection.from_settings(settings)
# Ensure the connection is working.
self.redis.ping()
#self.redis = settings.get("RCONN", redis.Redis(crawler.settings.get('REDIS_HOST', 'localhsot'), crawler.settings.get('REDIS_PORT', 6379)))
initCookie(self.redis, crawler.spider.name)
def from_settings(cls, settings):
kwargs = {
'persist': settings.getbool('SCHEDULER_PERSIST'),
'flush_on_start': settings.getbool('SCHEDULER_FLUSH_ON_START'),
'idle_before_close':
settings.getint('SCHEDULER_IDLE_BEFORE_CLOSE'),
}
# 如果缺少这些值，则意味着我们要使用默认值。
optional = {
# TODO: Use custom prefixes for this settings to note that are
# specific to scrapy-redis.
'queue_key': 'SCHEDULER_QUEUE_KEY',
'queue_cls': 'SCHEDULER_QUEUE_CLASS',
'dupefilter_key': 'SCHEDULER_DUPEFILTER_KEY',
# 我们使用默认设置名称来保持兼容性。
'dupefilter_cls': 'DUPEFILTER_CLASS',
'serializer': 'SCHEDULER_SERIALIZER',
}
for name, setting_name in optional.items():
val = settings.get(setting_name)
if val:
kwargs[name] = val
# 支持序列化程序作为模块的路径。
if isinstance(kwargs.get('serializer'), six.string_types):
kwargs['serializer'] = importlib.import_module(
kwargs['serializer'])
server = connection.from_settings(settings)
# 确保连接正常。
server.ping()
return cls(server=server, **kwargs)
def from_settings(cls, settings):
params = {}
params['client'] = connection.from_settings(settings) # from_settings means redis_from_settings
if settings.get("REDIS_SIMHASH_KEY"):
params['key'] = settings["REDIS_SIMHASH_KEY"]
return cls(**params)
def __init__(self):
settings = get_project_settings()
self.queue_key = settings.get('SCHEDULER_QUEUE_KEY', QUEUE_KEY)
self.server = connection.from_settings(settings)
self.headers = {
"Host": "www.zhihu.com",
"Connection": "keep-alive",
"Cache-Control": "max-age=0",
"Accept": "text/html,application/xhtml+xml,application/xml;q=0.9,image/webp,*/*;q=0.8",
"User-Agent": "Mozilla/5.0 (Windows NT 6.1; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/34.0.1847.131 Safari/537.36",
"Referer": "http://www.zhihu.com/people/raymond-wang",
"Accept-Encoding": "gzip,deflate,sdch",
"Accept-Language": "zh-CN,zh;q=0.8,en-US;q=0.6,en;q=0.4,zh-TW;q=0.2",
}
self.cookies = {
'_za': r'bda5810c-88f0-40a8-8d2b-d9be0e0c58a9',
'q_c1': r'28f9a453b53a482486644378553c3a10|1447162001000|1447162001000',
'_xsrf': r'4307a4b2977f25efbdacbd89edf2e789',
'cap_id': r'"OThkOGIwMDVkMDllNGZmMzkzN2JkY2MzNzhhMmZjZWQ=|1448186640|774a87a7e0bd5ecec150a0d4bed38b570859c822"',
'z_c0': r'"QUFBQUF1VWdBQUFYQUFBQVlRSlZUUjBnZVZZM0ptcEVROU9YSzZ3bXpUUEJXQm0zSUkxSFl3PT0=|1448186653|1eb9dfd0eff895cab5c818fd97d103a17d557dfe"',
'unlock_ticket': r'"QUFBQUF1VWdBQUFYQUFBQVlRSlZUU1dhVVZhcmFDck02VUROeVV3c1oyRHQ1aWduQmVLYWdRPT0=|1448186653|c734f11184740390f0b34536e218952aabdcff46"',
'__utmt': r'1',
'__utma': r'51854390.16347795.1448186642.1448186642.1448186642.1',
'__utmb': r'51854390.18.10.1448186642',
'__utmc': r'51854390',
'__utmz': r'51854390.1448186642.1.1.utmcsr=(direct)|utmccn=(direct)|utmcmd=(none)',
'__utmv': r'51854390.100-1|2=registration_date=20131118=1^3=entry_date=20131118=1'
}
super(ZhihuNotGenRequestSpider, self).__init__()
def from_settings(cls, settings):
server = connection.from_settings(settings)
# create one-time key. needed to support to use this
# class as standalone dupefilter with scrapy's default scheduler
# if scrapy passes spider on open() method this wouldn't be needed
key = "dupefilter:%s" % int(time.time())
return cls(server, key)
def test_redis_default(self):
settings = Settings()
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'localhost')
self.assertEqual(connect_args['port'], 6379)
def test_redis_default(self):
settings = Settings()
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'localhost')
self.assertEqual(connect_args['port'], 6379)
def from_settings(cls, settings):
params = {
'client': connection.from_settings(settings),
}
if settings.get('REDIS_SIMHASH_KEY'):
params['key'] = settings['REDIS_SIMHASH_KEY']
return cls(**params)
def from_crawler(cls, crawler):
settings = crawler.settings
server = connection.from_settings(settings)
s = cls(server, settings)
crawler.signals.connect(s.spider_opened, signal=signals.spider_opened)
crawler.signals.connect(s.spider_closed, signal=signals.spider_closed)
return s
def from_crawler(cls, crawler):
settings = crawler.settings
slave_key = settings.get('REDIS_START_URLS_KEY')
master_key = settings.get('REDIS_START_URLS_MASTER_KEY')
judge_key = settings.get('REDIS_JUDGE_KEY')
scan_page = settings.get('SCAN_PAGE')
server = connection.from_settings(settings)
s = cls(server, slave_key, master_key, judge_key, scan_page)
return s
def test_redis_host_port_fallback(self):
settings = Settings(
dict(REDIS_HOST='baz', REDIS_PORT=1337, REDIS_URL=None))
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'baz')
self.assertEqual(connect_args['port'], 1337)
def from_settings(cls, settings):
params = {
'client': connection.from_settings(settings),
}
if settings.get('REDIS_START_URLS_KEY'):
params['start_url_key'] = settings['REDIS_START_URLS_KEY']
if settings.get('REDIS_START_URLS_AS_SET'):
params['start_url_as_set'] = settings['REDIS_START_URLS_AS_SET']
return cls(**params)
def setup_redis(self, crawler=None):
"""Setup redis connection and idle signal.
This should be called after the spider has set its crawler object.
"""
if self.server is not None:
return
if crawler is None:
# We allow optional crawler argument to keep backwards
# compatibility.
# XXX: Raise a deprecation warning.
crawler = getattr(self, 'crawler', None)
if crawler is None:
raise ValueError("crawler is required")
settings = crawler.settings
if self.redis_key is None:
self.redis_key = settings.get(
'REDIS_START_URLS_KEY',
defaults.START_URLS_KEY,
)
self.redis_key = self.redis_key % {'name': self.name}
if not self.redis_key.strip():
raise ValueError("redis_key must not be empty")
if self.redis_batch_size is None:
# TODO: Deprecate this setting (REDIS_START_URLS_BATCH_SIZE).
self.redis_batch_size = settings.getint(
'REDIS_START_URLS_BATCH_SIZE',
settings.getint('CONCURRENT_REQUESTS'),
)
try:
self.redis_batch_size = int(self.redis_batch_size)
except (TypeError, ValueError):
raise ValueError("redis_batch_size must be an integer")
if self.redis_encoding is None:
self.redis_encoding = settings.get('REDIS_ENCODING',
defaults.REDIS_ENCODING)
self.logger.info(
"Reading start URLs from redis key '%(redis_key)s' "
"(batch size: %(redis_batch_size)s, encoding: %(redis_encoding)s)",
self.__dict__)
self.server = connection.from_settings(crawler.settings)
# The idle signal is called when the spider has no requests left,
# that's when we will schedule new requests from redis queue
crawler.signals.connect(self.spider_idle, signal=signals.spider_idle)
def from_settings(cls, settings):
params = {
'server': connection.from_settings(settings),
}
if settings.get('REDIS_ITEMS_KEY'):
params['key'] = settings['REDIS_ITEMS_KEY']
if settings.get('REDIS_ITEMS_SERIALIZER'):
params['serialize_func'] = load_object(
settings['REDIS_ITEMS_SERIALIZER'])
return cls(**params)
def test_redis_host_port(self):
settings = Settings({
'REDIS_HOST': 'localhost',
'REDIS_PORT': 9001,
})
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'localhost')
self.assertEqual(connect_args['port'], 9001)
def test_redis_host_port(self):
settings = Settings({
'REDIS_HOST': 'localhost',
'REDIS_PORT': 9001,
})
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'localhost')
self.assertEqual(connect_args['port'], 9001)
def test_redis_url(self):
settings = Settings({
'REDIS_URL': 'redis://*****:*****@localhost:9001/42',
})
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'localhost')
self.assertEqual(connect_args['port'], 9001)
self.assertEqual(connect_args['password'], 'bar')
self.assertEqual(connect_args['db'], 42)
def test_redis_host_port_fallback(self):
settings = Settings(dict(
REDIS_HOST='baz',
REDIS_PORT=1337,
REDIS_URL=None
))
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'baz')
self.assertEqual(connect_args['port'], 1337)
def test_redis_url(self):
settings = Settings({
'REDIS_URL': 'redis://*****:*****@localhost:9001/42',
})
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'localhost')
self.assertEqual(connect_args['port'], 9001)
self.assertEqual(connect_args['password'], 'bar')
self.assertEqual(connect_args['db'], 42)
def test_redis_url_precedence(self):
settings = Settings(
dict(REDIS_HOST='baz',
REDIS_PORT=1337,
REDIS_URL='redis://*****:*****@localhost:9001/42'))
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'localhost')
self.assertEqual(connect_args['port'], 9001)
self.assertEqual(connect_args['password'], 'bar')
self.assertEqual(connect_args['db'], 42)
class IsvServiceInfoFactorySpider(RedisSpider):
name = "isv_service_info_factory"
start_urls = [
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.CZ3Xrj&page_id=2489&isv_id=45632667&page_rank=2&tab_type=1'
]
redis_server = connection.from_settings(settings)
count = 0
def parse(self, response):
self.count = 0
self.redis_server.delete('isv_service_info:items')
self.redis_server.delete('isv_service_info:dupefilter')
self.redis_server.delete('isv_service_info:start_urls')
f = codecs.open('service-code-list.csv', 'r', 'utf-8')
for datas in f.readlines():
data = datas[:-1].split(',')
print data[1]
self.generate_url(data[0])
f.close()
def generate_url(self, service_code):
# 随机休眠0~1秒
time.sleep(random.random() * 3)
url = 'https://fuwu.taobao.com/ser/detail.html?service_code='
url += service_code
html = requests.get(url).text
selector = etree.HTML(html)
company_url = selector.xpath(
'//*[@id="apc-detail"]/div[1]/div/div/p[1]/a/@href')
# 防止没有公司服务列表只有服务详细页面
if not company_url:
self.redis_server.lpush('isv_service_info:start_urls', url)
return
company_url = company_url[0]
isv_id = re.search('isv_id=(.*?)&', company_url + '&').group(1)
company_url = 'https://fuwu.taobao.com/serv/shop_index.htm?isv_id='
company_url += isv_id
html = requests.get(company_url).text
selector = etree.HTML(html)
ul = selector.xpath('//*[@id="seller-header"]/div[2]/div[2]/div/ul/li')
for li in ul:
tab_type = li.xpath('span/b/a/text()')[0]
if '服务列表' == tab_type:
service_urls = li.xpath('span/b/a/@href')[0]
service_urls = 'https://fuwu.taobao.com/serv/' + service_urls
self.redis_server.lpush('isv_service_info:start_urls',
service_urls)
print service_urls
self.count += 1
print self.count
break
def setup_redis(self):
"""Setup redis connection and idle signal.
This should be called after the spider has set its crawler object.
"""
if not self.redis_key:
self.redis_key = '%s:start_urls' % self.name
self.server = connection.from_settings(self.crawler.settings)
# idle signal is called when the spider has no requests left,
# that's when we will schedule new requests from redis queue
self.crawler.signals.connect(self.spider_idle, signal=signals.spider_idle)
self.crawler.signals.connect(self.item_scraped, signal=signals.item_scraped)
log.msg("Reading URLs from redis list '%s'" % self.redis_key, level=log.INFO)
def test_redis_url_precedence(self):
settings = Settings(dict(
REDIS_HOST='baz',
REDIS_PORT=1337,
REDIS_URL='redis://*****:*****@localhost:9001/42'
))
server = connection.from_settings(settings)
connect_args = server.connection_pool.connection_kwargs
self.assertEqual(connect_args['host'], 'localhost')
self.assertEqual(connect_args['port'], 9001)
self.assertEqual(connect_args['password'], 'bar')
self.assertEqual(connect_args['db'], 42)
def __init__(self, settings):
self.request_count = settings.getint('MYEXT_ITEMCOUNT', 1000)
self.request_num = 0
# self.scheduler = scheduler
self.request = None
self.no_meet = True#是否遇到seed请求
self.path_base = settings.get("SEED_FILE_PATH")
self.server = connection.from_settings(settings)
use_set = settings.getbool('REDIS_START_URLS_AS_SET', defaults.START_URLS_AS_SET)
request_set = settings.get("SCHEDULER_QUEUE_CLASS")
self.fetch_one = self.server.spop if use_set else self.server.lpop
self.add_one = self.server.sadd if use_set else self.server.lpush
self.get_num = self.server.llen if "LifoQueue" in request_set or "FifoQueue" in request_set else self.server.zcard
self.get_startnum = self.server.scard if use_set else self.server.llen
self.split_num = settings.get("SPLIT_NUM")
self.path_split = None
class IsvServiceInfoFactorySpider(RedisSpider):
name = "cycle_run"
start_urls = [
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.CZ3Xrj&page_id=2489&isv_id=45632667&page_rank=2&tab_type=1'
]
redis_server = connection.from_settings(settings)
def parse(self, response):
self.runTask(self.work, hour=4)
def work(self):
self.redis_server.lpush(
'isv_service_info_factory:start_urls',
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.CZ3Xrj&page_id=2489&isv_id=45632667&page_rank=2&tab_type=1'
)
print "更新周期到"
def runTask(self, func, day=0, hour=0, min=0, second=0):
# Init time
now = datetime.now()
strnow = now.strftime('%Y-%m-%d %H')
# print "now:", strnow
# First next run time
period = timedelta(days=day, hours=hour, minutes=min, seconds=second)
next_time = now + period
strnext_time = next_time.strftime('%Y-%m-%d %H')
# print "next run:", strnext_time
while True:
# Get system current time
iter_now = datetime.now()
iter_now_time = iter_now.strftime('%Y-%m-%d %H')
if str(iter_now_time) == str(strnext_time):
# Get every start work time
# print "start work: %s" % iter_now_time
# Call task func
func()
# print "task done."
# Get next iteration time
iter_time = iter_now + period
strnext_time = iter_time.strftime('%Y-%m-%d %H')
# print "next_iter: %s" % strnext_time
# Continue next iteration
continue
# 1分钟检查一次
time.sleep(600)
def setup_redis(self):
"""Setup redis connection and idle signal.
This should be called after the spider has set its crawler object.
"""
if not self.redis_key:
self.redis_key = '%s:start_urls' % self.name
self.server = connection.from_settings(self.crawler.settings)
# idle signal is called when the spider has no requests left,
# that's when we will schedule new requests from redis queue
self.crawler.signals.connect(self.spider_idle,
signal=signals.spider_idle)
self.crawler.signals.connect(self.item_scraped,
signal=signals.item_scraped)
# self.crawler.signals.connect(self.engine_stopped, signal=signals.engine_stopped)
# self.crawler.signals.connect(self.spider_closed, signal=signals.spider_closed)
self.log("Reading URLs from redis list '%s'" % self.redis_key)
class GxzfcgFactorySpider(RedisSpider):
name = "gxzfcg_factory"
name_pre = 'gxzfcg'
# allowed_domains = ["dmoz.org"]
start_urls = [
"http://www.gxzfcg.gov.cn/CmsNewsController/recommendBulletinList/channelCode-cgxx/20/page_1.html"
]
redis_server = connection.from_settings(settings)
def parse(self, response):
level_xpaths = [
"//*[@id=\"bodyMain\"]/div/aside/div/nav/ul/li[1]/ul/li",
"//*[@id=\"bodyMain\"]/div/aside/div/nav/ul/li[2]/ul/li"
]
level_names = ["区本级采购", "市(县)级采购"]
i = 0
for level_xpath in level_xpaths:
level_name = level_names[i]
i += 1
ul = response.xpath(level_xpath)
for li in ul:
item = TenderItem()
item['node_name'] = settings['NODE_NAME']
item['website'] = '广西壮族自治区政府采购网'
item['level'] = level_name
item['type'] = li.xpath("a/text()").extract()[0]
next_page_url = 'http://www.gxzfcg.gov.cn' + li.xpath(
"a/@href").extract()[0]
yield scrapy.Request(next_page_url,
callback=self.parse_news,
meta={'item': item})
def parse_news(self, response):
page_nums = re.search(
u'页次：1/(.*?)页',
response.xpath("//*[@id=\"QuotaList_paginate\"]/span[1]/text()").
extract()[0]).group(1)
for page_num in range(1, int(page_nums) + 1):
next_page_url = re.sub('page_(.*?).html',
'page_' + str(page_num) + '.html',
response.url)
self.redis_server.lpush('%s_spider:start_urls' % self.name_pre,
next_page_url)
print next_page_url
def from_settings(cls, settings):
if os.environ.get('spider_set_persist'):
persist = (os.environ.get('spider_set_persist') != 'False')
else:
persist = settings.get('SCHEDULER_PERSIST', SCHEDULER_PERSIST)
if os.environ.get('need_dupefilter'):
need_dupefilter = (os.environ.get('need_dupefilter') != 'False')
else:
need_dupefilter = True
queue_key = settings.get('SCHEDULER_QUEUE_KEY', QUEUE_KEY)
queue_cls = load_object(
settings.get('SCHEDULER_QUEUE_CLASS', QUEUE_CLASS))
dupefilter_key = settings.get('DUPEFILTER_KEY', DUPEFILTER_KEY)
idle_before_close = settings.get('SCHEDULER_IDLE_BEFORE_CLOSE',
IDLE_BEFORE_CLOSE)
server = connection.from_settings(settings)
return cls(server, persist, queue_key, queue_cls, dupefilter_key,
idle_before_close, need_dupefilter)
def setup_redis(self):
"""Setup redis connection and idle signal.
This should be called after the spider has set its crawler object.
"""
if not self.redis_key:
self.redis_key = "%s:start_urls" % self.name
self.server = connection.from_settings(self.crawler.settings)
# idle signal is called when the spider has no requests left,
# that's when we will schedule new requests from redis queue
self.crawler.signals.connect(self.spider_idle, signal=signals.spider_idle)
self.crawler.signals.connect(self.schedule_rest_requests, signal=signals.item_scraped)
self.crawler.signals.connect(self.schedule_rest_requests, signal=signals.item_dropped)
self.crawler.signals.connect(self.schedule_rest_requests, signal=signals.request_scheduled)
self.crawler.signals.connect(self.schedule_rest_requests, signal=signals.response_received)
self.crawler.signals.connect(self.schedule_rest_requests, signal=signals.response_downloaded)
self.crawler.signals.connect(self.__start_loop, signal=signals.spider_opened)
self.crawler.signals.connect(self.__stop_loop, signal=signals.spider_closed)
log.msg("Reading URLs from redis list '%s'" % self.redis_key, level=log.INFO)
self.touch()
def from_settings(cls, settings):
params = {
'redis_conn': connection.from_settings(settings)
}
return cls(**params)
def test_default_params(self):
server = from_settings(self.settings)
assert server is self.redis_cls.return_value
self.redis_cls.assert_called_with(**dict(defaults.REDIS_PARAMS, **self.expected_params))
def test_redis_cls_custom_path(self):
self.settings['REDIS_PARAMS']['redis_cls'] = 'mock.Mock'
server = from_settings(self.settings)
assert isinstance(server, mock.Mock)
def test_redis_cls_default(self):
server = from_settings(Settings())
assert isinstance(server, defaults.REDIS_CLS)
from scrapy_redis import connection
from scrapy.conf import settings
import time
redis_server = connection.from_settings(settings)
redis_server.lpush('isv_service_info_factory:start_urls',
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.CZ3Xrj&page_id=2489&isv_id=45632667&page_rank=2&tab_type=1')
print "更新周期到"
time.sleep(2)
def get_server(settings):
redis_server = connection.from_settings(settings)
return redis_server
def from_settings(cls, settings):
server = connection.from_settings(settings)
return cls(server)
def _set_crawler(self, crawler):
super(HomepageSpider, self)._set_crawler(crawler)
self.server = connection.from_settings(self.crawler.settings)
def test_default_params(self):
server = from_settings(self.settings)
assert server is self.redis_cls.return_value
self.redis_cls.assert_called_with(**dict(DEFAULT_PARAMS, **self.expected_params))
class IsvServiceInfoSpider(RedisSpider):
name = "isv_service_info"
start_urls = [
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.CZ3Xrj&page_id=2489&isv_id=45632667&page_rank=2&tab_type=1',
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.Oquk72&page_id=678230&isv_id=877021141&page_rank=2&tab_type=1',
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.mSxKHl&page_id=25995&isv_id=305442977&page_rank=2&tab_type=1',
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.lH8xCC&page_id=172044&isv_id=570102268&page_rank=2&tab_type=1',
'https://fuwu.taobao.com/serv/shop_index.htm?spm=0.0.0.0.OzhuHM&page_id=690262&isv_id=897211958&page_rank=2&tab_type=1'
]
redis_server = connection.from_settings(settings)
def parse(self, response):
print response.url
item = IsvServiceInfoItem()
isv_id = re.search('isv_id=(.*?)&', response.url + '&').group(1)
company_name = response.xpath(
'//*[@id="seller-header"]/div[1]/div/a/text()').extract()[0]
servers = response.xpath('//*[@id="searchForm"]/div[2]/table/tbody/tr')
for server in servers:
user_number = server.xpath('td[4]/text()').extract()[0]
browser_number = server.xpath('td[5]/text()').extract()[0]
item['isv_id'] = isv_id
item['company_name'] = company_name
item['user_number'] = user_number
item['browser_number'] = browser_number
detail_url = re.sub(
'service/service.htm', 'ser/detail.html',
'https:' + server.xpath('td[2]/dl/dt/a/@href').extract()[0])
yield scrapy.Request(detail_url,
callback=self.parse_detail,
meta={'item': item})
print detail_url
def parse_detail(self, response):
detail_url = response.url
service_code = re.search('service_code=(.*?)&',
detail_url + '&').group(1)
content = response.xpath('//*[@id="J_SKUForm"]/div[2]/text()')
# print(content)
# 判断是否存在"此服务暂不支持在线订购，请您直接联系服务商"
if not content:
service_name = response.xpath(
'//*[@id="J_SKUForm"]/div[1]/h2/text()').extract()[0].replace(
'\t', '').replace('\n', '')
score = response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/span[2]/text()'
).extract()[0]
usability = response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[1]/li[1]/span[2]/@class'
).extract()[0]
usability_compare = \
response.xpath('//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[1]/li[1]/span[2]/text()').extract()[0]
# 判断是高于还是低于
if usability == 'low per':
usability_compare = '-' + usability_compare
attitude = response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[1]/li[2]/span[2]/@class'
).extract()[0]
attitude_compare = \
response.xpath('//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[1]/li[2]/span[2]/text()').extract()[0]
if attitude == 'low per':
attitude_compare = '-' + attitude_compare
stability = response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[1]/li[3]/span[2]/@class'
).extract()[0]
stability_compare = \
response.xpath('//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[1]/li[3]/span[2]/text()').extract()[0]
if stability == 'low per':
stability_compare = '-' + stability_compare
secure_score = str(
response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[2]/li[1]/span[2]/text()'
).extract()[0]).replace('\t', '').replace('\n', '')
payer_number = response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[2]/li[2]/span[2]/text()'
).extract()[0]
nearly_payer_number = \
response.xpath('//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[2]/li[2]/span[3]/text()').extract()[0]
continue_rate = response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[2]/li[3]/span[2]/text()'
).extract()[0]
refund_rate = response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[2]/li[4]/span[2]/text()'
).extract()[0]
open_rate = response.xpath(
'//*[@id="apc-detail"]/div[2]/div[1]/div[2]/div/ul[2]/li[5]/span[2]/text()'
)
# 打开率有点特殊
if open_rate:
open_rate = open_rate.extract()[0]
else:
open_rate = None
score_times = re.search(
'(\d+)',
response.xpath(
'//*[@id="reviews"]/div[1]/div/div/div[2]/span/text()').
extract()[0]).group(1)
five_score_rate = \
response.xpath('//*[@id="reviews"]/div[1]/div/div/div[3]/ul/li[1]/span[@class="tb-r-pecent"]/text()').extract()[0].replace('\t', '').replace('\n', '')
four_score_rate = \
response.xpath('//*[@id="reviews"]/div[1]/div/div/div[3]/ul/li[2]/span[@class="tb-r-pecent"]/text()').extract()[0].replace('\t', '').replace('\n', '')
three_score_rate = \
response.xpath('//*[@id="reviews"]/div[1]/div/div/div[3]/ul/li[3]/span[@class="tb-r-pecent"]/text()').extract()[0].replace('\t', '').replace('\n', '')
two_score_rate = \
response.xpath('//*[@id="reviews"]/div[1]/div/div/div[3]/ul/li[4]/span[@class="tb-r-pecent"]/text()').extract()[0].replace('\t', '').replace('\n', '')
one_score_rate = \
response.xpath('//*[@id="reviews"]/div[1]/div/div/div[3]/ul/li[5]/span[@class="tb-r-pecent"]/text()').extract()[0].replace('\t', '').replace('\n', '')
seller_rank_percent_url = 'https://fuwu.taobao.com' + \
response.xpath('//*[@id="desc-log"]/div/div[1]/div[1]/h5/a/@href').extract()[0]
seller_industry_percent_url = 'https://fuwu.taobao.com' + \
response.xpath('//*[@id="desc-log"]/div/div[1]/div[2]/h5/a/@href').extract()[0]
# 爬淘宝买家等级占比
html = requests.get(seller_rank_percent_url).text
selector = etree.HTML(html)
seller_rank_percent_trs = selector.xpath(
'//*[@id="apc-detail"]/div[2]/table/tbody/tr')
seller_rank_percent = '['
for seller_rank_percent_tr in seller_rank_percent_trs:
seller_rank_percent_tds = seller_rank_percent_tr.xpath('td')
index = 0
for seller_rank_percent_td in seller_rank_percent_tds:
index += 1
img = seller_rank_percent_td.xpath('img/@src')
if img:
seller_rank = re.search('rank/(.*?).gif',
img[0]).group(1)
else:
seller_rank = seller_rank_percent_td.xpath('text()')
if seller_rank:
seller_rank = str(seller_rank[0]).replace(
'\t', '').replace('\n', '').replace(' ', '')
if seller_rank:
if index % 2 == 1:
seller_rank_percent = seller_rank_percent + '{\"rank\":\"' + str(
seller_rank).replace('\r', '') + '\",'
else:
seller_rank_percent = seller_rank_percent + '\"percent\":\"' + seller_rank + '\"},'
seller_rank_percent = seller_rank_percent[:-1] + ']'
# 爬卖家行业占比
html = requests.get(seller_industry_percent_url).text
selector = etree.HTML(html)
seller_industry_percent_trs = selector.xpath(
'//*[@id="apc-detail"]/div[2]/table/tbody/tr')
seller_industry_percent = '['
for seller_industry_percent_tr in seller_industry_percent_trs:
seller_industry_percent_tds = seller_industry_percent_tr.xpath(
'td')
index = 0
for seller_industry_percent_td in seller_industry_percent_tds:
index += 1
img = seller_industry_percent_td.xpath('img/@src')
if img:
seller_rank = re.search('rank/(.*?).gif',
img[0]).group(1)
else:
seller_rank = seller_industry_percent_td.xpath(
'text()')
if seller_rank:
seller_rank = str(seller_rank[0]).replace(
'\t', '').replace('\n', '').replace(' ', '')
if seller_rank:
if index % 2 == 1:
seller_industry_percent = seller_industry_percent + '{\"industry\":\"' + str(
seller_rank).replace('\r', '') + '\",'
else:
seller_industry_percent = seller_industry_percent + '\"percent\":\"' + seller_rank + '\"},'
seller_industry_percent = seller_industry_percent[:-1] + ']'
# print(company_name)
print(service_name)
print(service_code)
print(score)
print(usability)
print(usability_compare)
print(attitude)
print(attitude_compare)
print(stability)
print(stability_compare)
print(secure_score)
print(payer_number)
print(nearly_payer_number)
print(continue_rate)
print(refund_rate)
print(open_rate)
print(score_times)
print(five_score_rate)
print(four_score_rate)
print(three_score_rate)
print(two_score_rate)
print(one_score_rate)
# print(seller_rank_percent_url)
# print(seller_industry_percent_url)
print(seller_rank_percent)
print(seller_industry_percent)
# print(user_number)
# print(browser_number)
now_time = datetime.datetime.today()
item = response.meta['item']
item['add_time'] = now_time
item['modify_time'] = now_time
# item['isv_id'] = isv_id
# item['company_name'] = company_name
item['service_name'] = service_name
item['service_code'] = service_code
item['score'] = score
# item['usability'] = usability
item['usability_compare'] = usability_compare
# item['attitude'] = attitude
item['attitude_compare'] = attitude_compare
# item['stability'] = stability
item['stability_compare'] = stability_compare
item['secure_score'] = secure_score
item['payer_number'] = payer_number
item['nearly_payer_number'] = nearly_payer_number
item['continue_rate'] = continue_rate
item['refund_rate'] = refund_rate
item['open_rate'] = open_rate
item['score_times'] = score_times
item['five_score_rate'] = five_score_rate
item['four_score_rate'] = four_score_rate
item['three_score_rate'] = three_score_rate
item['two_score_rate'] = two_score_rate
item['one_score_rate'] = one_score_rate
item['seller_rank_percent'] = seller_rank_percent
item['seller_industry_percent'] = seller_industry_percent
# item['user_number'] = user_number
# item['browser_number'] = browser_number
yield item
def from_settings(cls, settings):
params = {
'server': connection.from_settings(settings),
}
return cls(**params)
class ShopBasicInfoSpider(RedisSpider):
name = "shop_basic_info"
start_urls = []
redis_server = connection.from_settings(settings)
def parse(self, response):
head = {'User-Agent': \
'Mozilla/5.0 (Windows NT 6.3; WOW64) AppleWebKit/537.36 (KHTML, like Gecko) Chrome/49.0.2623.112 Safari/537.36',
'cookie': 'cna=9dmhD/z0ODgCATHd1PgOvAEo; ali_ab=49.221.212.248.1461498199870.2; hng=CN%7Czh-cn%7CCNY; thw=cn; isg=0402F5E80881A216E6813A6676800CB8; v=0; _tb_token_=ku02IolX76m3jJ; uc1=cookie14=UoWxMP74ys3MPA%3D%3D&existShop=false&cookie16=WqG3DMC9UpAPBHGz5QBErFxlCA%3D%3D&cookie21=VFC%2FuZ9aiKCaj7AzN6nc&tag=1&cookie15=V32FPkk%2Fw0dUvg%3D%3D&pas=0; uc3=sg2=UIS5OL%2BOEDgy%2FIeQ7IgTu7dSOvuG0LEay5288ZRYw64%3D&nk2=pbEaPGpOBJk%3D&id2=UoYfobtYhLxhEw%3D%3D&vt3=F8dASmgu7PcOeAskyes%3D&lg2=UtASsssmOIJ0bQ%3D%3D; existShop=MTQ2MTkyMDU3MA%3D%3D; uss=UIIpyK78%2BArm1rQcpUrk%2FRwXHQDc93OpxAQgdlu7DWHJVDuJuqKSxy5hBg%3D%3D; lgc=%5Cu4F01%5Cu513F%5Cu8469%5Cu8469; tracknick=%5Cu4F01%5Cu513F%5Cu8469%5Cu8469; cookie2=1cd8c28594101548f03793d63c556c34; sg=%E8%91%A937; mt=np=&ci=9_1&cyk=-1_-1; cookie1=Vvkh3e1O2MWb%2FWoyF7KMYkHR3r9XP1ItH8ivkdLbbCM%3D; unb=1710468073; skt=6e1a6a704a8e0ddd; t=a74cdfe08cedf1981150320f20e9a793; _cc_=U%2BGCWk%2F7og%3D%3D; tg=0; _l_g_=Ug%3D%3D; _nk_=%5Cu4F01%5Cu513F%5Cu8469%5Cu8469; cookie17=UoYfobtYhLxhEw%3D%3D; l=Av7-AatB1kluKMPP1QNNkk-Bzh5BL8LA'
}
seller_nick = urllib.unquote(
re.search('&q=(.*?)&',
response.url + '&').group(1)).decode('utf-8')
print seller_nick
html = response.body
content = re.search('g_page_config = (.*?);\n', html, re.S)
while not content:
html = requests.get(response.url, headers=head).text
content = re.search('g_page_config = (.*?);\n', html, re.S)
content = content.group(1)
# 解析出全部店铺列表信息的json
data = json.loads(content).get('mods').get('shoplist').get('data')
# 判断搜索有没有结果
if data is not None:
the_shop_data = data.get('shopItems')[0]
nick = the_shop_data.get('nick')
# 第一个店铺的nick要跟给定的nick相等
if nick == seller_nick:
shop_type = the_shop_data.get('shopIcon').get(
'iconClass').strip()
shop_name = the_shop_data.get('rawTitle').strip()
shop_id = the_shop_data.get('nid').strip()
shop_address = the_shop_data.get('provcity').strip()
total_sold = int(the_shop_data.get('totalsold'))
goods_number = int(the_shop_data.get('procnt'))
shop_label = ''
icons = the_shop_data.get('icons')
for i in icons:
shop_label = shop_label + i.get('title') + ','
if len(shop_label) > 0:
shop_label = shop_label[:-1]
good_rate_percent = float(
self.delete_the_percent(
the_shop_data.get('goodratePercent')))
shop_img_url = the_shop_data.get('picUrl').strip()
shop_rate_url = the_shop_data.get('userRateUrl').strip()
dsrStr = json.loads(the_shop_data.get('dsrInfo').get('dsrStr'))
main_business = dsrStr.get('ind').strip()
if main_business == '':
main_business = None
describe_score_industry = self.delete_the_percent(
dsrStr.get('mg'))
service_score_industry = self.delete_the_percent(
dsrStr.get('sg'))
logistics_score_industry = self.delete_the_percent(
dsrStr.get('cg'))
# 判断店铺等级是否为0
if shop_type != 'rank seller-rank-0':
url = 'https:' + shop_rate_url
html = requests.get(url, headers=head)
add_time = datetime.datetime.today()
modify_time = add_time
is_exist = True
deposit = None
seller_rank = None
buyer_rank = None
main_rate = None
# 切割地址
if shop_address != '':
shop_address_s = str(shop_address).split(' ')
if len(shop_address_s) == 2:
shop_address_province = shop_address_s[0]
shop_address_city = shop_address_s[1]
elif len(shop_address_s) == 1:
shop_address_province = shop_address_s[0]
shop_address_city = None
else:
shop_address_province = None
shop_address_city = None
if shop_type != 'icon-service-tianmao-large':
if shop_type == 'icon-service-qiye-large':
shop_type = '企业店铺'
else:
shop_type = '普通店铺'
else:
shop_type = '天猫店铺'
item = ShopbasicinfoItem()
item['add_time'] = add_time
item['modify_time'] = modify_time
item['nick'] = nick
item['shop_type'] = shop_type
item['shop_name'] = shop_name
item['shop_id'] = shop_id
item['shop_address_province'] = shop_address_province
item['shop_address_city'] = shop_address_city
item['total_sold'] = total_sold
item['goods_number'] = goods_number
item['good_rate_percent'] = good_rate_percent
item['shop_img_url'] = shop_img_url
item['shop_rate_url'] = shop_rate_url
item['main_business'] = main_business
item['deposit'] = deposit
item['seller_rank'] = seller_rank
item['buyer_rank'] = buyer_rank
item['main_rate'] = main_rate
item['is_exist'] = is_exist
item['shop_label'] = shop_label
yield item
def getContent(self, content):
if content:
return content[0]
return None
def getNumber(self, content):
if content:
result = re.search('(\d+)', content[0])
if result:
return float(result.group(1))
return 0
def getUserId(self, content):
content = re.search('"userID": "(.*?)"', content)
if content:
return content.group(1)
return None
def getCharge(self, content):
content = re.search('￥(.*)', self.getContent(content))
if content:
return float(content.group(1).replace(',', ''))
return 0
def delete_the_percent(self, content):
if content:
content = re.search('(.*)%', content)
if content:
print('###' + content.group(1))
return float(content.group(1))
return 0
def delete_the_fen(self, content):
if content:
content = re.search('(.*)分', content)
if content:
print('fen' + content.group(1))
return float(content.group(1))
return 0
def delete_the_tian(self, content):
if content:
content = re.search('(.*)天', content)
if content:
print('天' + content.group(1))
return float(content.group(1))
return 0
